Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Sam Altman recently said: “GPT-OSS has strong real-world performance comparable to o4-mini—and you can run it locally on your phone.” Many believed running a 20B-parameter model on mobile devices was still years away. At Nexa AI, we’ve built our foundation on deep on-device AI technology—turning that vision into reality....

nexa_ai's profile picture

NEXA AI

2,323 subscribers

197,453 Aufrufe • vor 8 Monaten •via X (Twitter)

Gesundheit & WellnessWissenschaft & TechnologieBildung
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

A voice agent powered by gpt-oss. Running locally on my macBook. Demo recorded in a Waymo with WiFi turned off. I'm still on my space game voice AI kick, obviously. Code link below. For conversational voice AI, you want to set the gpt-oss reasoning behavior to "low". (The default is "medium".) Notes on how to do that and a jinja template you can use are in the repo. The LLM in the demo video is the big, 120B version of gpt-oss. You can use the smaller, 20B model for this, of course. But OpenAI really did a cool thing here designing the 120B model to run in "just" 80GB of VRAM. And the llama.cpp mlx inference is fast: ~250ms TTFT. Running a big model on-device feels like a time warp into the future of AI.
4:35

A voice agent powered by gpt-oss. Running locally on my macBook. Demo recorded in a Waymo with WiFi turned off. I'm still on my space game voice AI kick, obviously. Code link below. For conversational voice AI, you want to set the gpt-oss reasoning behavior to "low". (The default is "medium".) Notes on how to do that and a jinja template you can use are in the repo. The LLM in the demo video is the big, 120B version of gpt-oss. You can use the smaller, 20B model for this, of course. But OpenAI really did a cool thing here designing the 120B model to run in "just" 80GB of VRAM. And the llama.cpp mlx inference is fast: ~250ms TTFT. Running a big model on-device feels like a time warp into the future of AI.

kwindla

202,113 Aufrufe • vor 10 Monaten

A big milestone for AI on Windows: gpt‑oss‑20b is now available in Windows AI Foundry and Azure AI Foundry! You can now run this open-source, frontier-class model locally on a high-performance Windows PC. It’s fast, capable, and built for real-world use. Brought to life through collaboration across Windows, Azure, and OpenAI teams. We can’t wait to see what you create. 🚀
0:35

A big milestone for AI on Windows: gpt‑oss‑20b is now available in Windows AI Foundry and Azure AI Foundry! You can now run this open-source, frontier-class model locally on a high-performance Windows PC. It’s fast, capable, and built for real-world use. Brought to life through collaboration across Windows, Azure, and OpenAI teams. We can’t wait to see what you create. 🚀

Pavan Davuluri

80,597 Aufrufe • vor 10 Monaten

We’re excited to partner with OpenAI to launch their new open source models natively on Databricks! gpt-oss sets a new standard of quality for open language models, supporting advanced reasoning with the transparency, flexibility and control enterprises need. Running on Databricks, the gpt-oss models connect securely to your data and scale with built-in governance, and expand what you can build and do with GenAI. Try both the 20B and 120B today in the Mosaic AI Playground.
0:39

We’re excited to partner with OpenAI to launch their new open source models natively on Databricks! gpt-oss sets a new standard of quality for open language models, supporting advanced reasoning with the transparency, flexibility and control enterprises need. Running on Databricks, the gpt-oss models connect securely to your data and scale with built-in governance, and expand what you can build and do with GenAI. Try both the 20B and 120B today in the Mosaic AI Playground.

Databricks

10,086 Aufrufe • vor 10 Monaten

Today’s a big day! We have something really exciting to share with the open-source community. We’re launching two open-weight language models: gpt-oss-120b and gpt-oss-20b. They’re incredible models, built for developers, trained for reasoning, efficiency, and real-world use.🧵
0:59

Today’s a big day! We have something really exciting to share with the open-source community. We’re launching two open-weight language models: gpt-oss-120b and gpt-oss-20b. They’re incredible models, built for developers, trained for reasoning, efficiency, and real-world use.🧵

Romain Huet

34,187 Aufrufe • vor 10 Monaten

AI is now FREE!! Genspark AI Browser now offers the world's first on-device free AI. - Zero internet required, run models locally on your machine - Download 169 open-weight models (GPT-OSS, Gemma3, etc.) - Private & Fast. Forever free for everyone. 1/3
1:40

AI is now FREE!! Genspark AI Browser now offers the world's first on-device free AI. - Zero internet required, run models locally on your machine - Download 169 open-weight models (GPT-OSS, Gemma3, etc.) - Private & Fast. Forever free for everyone. 1/3

Eric Jing

547,839 Aufrufe • vor 9 Monaten

So how good is gpt-oss at function calling for real use cases and how to implement it correctly on Groq? Meet Autosheet: a GroqLabs project to showcase gpt-oss models running on Groq Inc! It's a browser spreadsheet driven by AI with built-in MCP server support. A video & 🧵
5:58

So how good is gpt-oss at function calling for real use cases and how to implement it correctly on Groq? Meet Autosheet: a GroqLabs project to showcase gpt-oss models running on Groq Inc! It's a browser spreadsheet driven by AI with built-in MCP server support. A video & 🧵

Rick Lamers

26,321 Aufrufe • vor 10 Monaten

The next generation of mobile apps will run multimodal AI locally by default. Today, we’re making it practical for developers to ship. We just launched NexaSDK for Mobile on Product Hunt. Developers can run the latest multimodal AI models fully on-device in iOS & Android apps with Apple Neural Engine and Qualcomm Hexagon NPU acceleration. In just 3 lines of code, build chat, multimodal, search, and audio features with no cloud cost, complete privacy, 2x faster speed and 9× better energy efficiency. Try out NexaSDK for Mobile and we’d love your feedback (Product Hunt link in thread).
1:21

The next generation of mobile apps will run multimodal AI locally by default. Today, we’re making it practical for developers to ship. We just launched NexaSDK for Mobile on Product Hunt. Developers can run the latest multimodal AI models fully on-device in iOS & Android apps with Apple Neural Engine and Qualcomm Hexagon NPU acceleration. In just 3 lines of code, build chat, multimodal, search, and audio features with no cloud cost, complete privacy, 2x faster speed and 9× better energy efficiency. Try out NexaSDK for Mobile and we’d love your feedback (Product Hunt link in thread).

NEXA AI

319,337 Aufrufe • vor 6 Monaten

✨ Personal AI is the next computing platform. AI is shifting from something you access to something you build with, locally, at the edge, and across systems. We’re unlocking new possibilities for developers: • AMD Ryzen AI Halo, a local-first developer system, preorder starting in June, develop AI without limits on your desk • Gorgon Halo with up to 192GB unified memory, supporting 300B+ parameter models locally, run massive models locally We’re excited to partner with clem 🤗🤗, Co-founder and CEO of Hugging Face, to advance open-source AI for Ryzen AI. Our focus is seamless AI, from model to deployment. Cloud, edge, device. One continuum. Multi-agent systems, local inference at scale, open models as infrastructure. This is the next computing era 🚀
4:49

✨ Personal AI is the next computing platform. AI is shifting from something you access to something you build with, locally, at the edge, and across systems. We’re unlocking new possibilities for developers: • AMD Ryzen AI Halo, a local-first developer system, preorder starting in June, develop AI without limits on your desk • Gorgon Halo with up to 192GB unified memory, supporting 300B+ parameter models locally, run massive models locally We’re excited to partner with clem 🤗🤗, Co-founder and CEO of Hugging Face, to advance open-source AI for Ryzen AI. Our focus is seamless AI, from model to deployment. Cloud, edge, device. One continuum. Multi-agent systems, local inference at scale, open models as infrastructure. This is the next computing era 🚀

Jack Huynh

47,611 Aufrufe • vor 1 Monat

GT Protocol AI Digest No.82: AI Starts Running the System Here are five stories worth your attention 👇 💻 NVIDIA Pushes AI to Your Device NVIDIA showcased RTX PCs and DGX systems that can run AI models and agents locally. The shift is important. AI is no longer tied to the cloud, it is moving directly onto user devices. 🧠 Gemini Becomes Personal Google is rolling out personalized Gemini across the US. The assistant adapts to your context and activity, turning AI from a generic tool into a persistent, tailored system. 🎨 Adobe Lets You Train Your Own AI Adobe now allows users to train Firefly models on their own artwork. This gives creators more control over style, but also raises new questions around ownership and dataset boundaries. ⚡️ Smaller GPT-5.4 Models Go Wide OpenAI introduced GPT-5.4 mini and nano, optimized for efficiency and broader deployment. Strong models are no longer limited to heavy infrastructure. 💳 Visa Prepares for AI Payments Visa is building systems for transactions initiated by AI agents. This moves AI beyond interfaces and into real economic activity. Read the full digest on our Medium 👉
0:44

GT Protocol AI Digest No.82: AI Starts Running the System Here are five stories worth your attention 👇 💻 NVIDIA Pushes AI to Your Device NVIDIA showcased RTX PCs and DGX systems that can run AI models and agents locally. The shift is important. AI is no longer tied to the cloud, it is moving directly onto user devices. 🧠 Gemini Becomes Personal Google is rolling out personalized Gemini across the US. The assistant adapts to your context and activity, turning AI from a generic tool into a persistent, tailored system. 🎨 Adobe Lets You Train Your Own AI Adobe now allows users to train Firefly models on their own artwork. This gives creators more control over style, but also raises new questions around ownership and dataset boundaries. ⚡️ Smaller GPT-5.4 Models Go Wide OpenAI introduced GPT-5.4 mini and nano, optimized for efficiency and broader deployment. Strong models are no longer limited to heavy infrastructure. 💳 Visa Prepares for AI Payments Visa is building systems for transactions initiated by AI agents. This moves AI beyond interfaces and into real economic activity. Read the full digest on our Medium 👉

GT Protocol

40,065 Aufrufe • vor 3 Monaten

Behold... GPT-OSS (20B) running 100% locally in your browser on WebGPU. This shouldn't be possible — but with Transformers.js v4 and ONNX Runtime Web, it is! A new class of AI apps is emerging. Zero-install, infinite distribution. Simply visit a website and run models locally.
1:23

Behold... GPT-OSS (20B) running 100% locally in your browser on WebGPU. This shouldn't be possible — but with Transformers.js v4 and ONNX Runtime Web, it is! A new class of AI apps is emerging. Zero-install, infinite distribution. Simply visit a website and run models locally.

Xenova

311,512 Aufrufe • vor 4 Monaten

OpenAI has finally released GPT OSS 20B!! This is probably the most powerful model you can run locally on a laptop. → Only 3.6B active parameters → Adjustable "Reasoning Effort" → Works with 16GB of RAM! Quick steps to use it 100% free and offline:
0:29

OpenAI has finally released GPT OSS 20B!! This is probably the most powerful model you can run locally on a laptop. → Only 3.6B active parameters → Adjustable "Reasoning Effort" → Works with 16GB of RAM! Quick steps to use it 100% free and offline:

Paul Couvert

595,522 Aufrufe • vor 10 Monaten

Sam Altman says the goal is to run a GPT-5 quality model locally on a single device We don't know how to do it yet, but the recent efficiency gains were also once thought impossible The vision is a new computer form factor for the AI era: "it should run locally... if you want it to"
0:47

Sam Altman says the goal is to run a GPT-5 quality model locally on a single device We don't know how to do it yet, but the recent efficiency gains were also once thought impossible The vision is a new computer form factor for the AI era: "it should run locally... if you want it to"

Haider.

197,374 Aufrufe • vor 7 Monaten

Bringing AI agents to the PC requires efficiency, speed, and smart memory management. AMD and Liquid AI are partnering to enable foundational models on PCs and end-point devices to address the real-world challenges of running AI agents locally. Liquid AI Co-founder and CEO Ramin explains how we are helping make on-device AI practical and accessible.
0:47

Bringing AI agents to the PC requires efficiency, speed, and smart memory management. AMD and Liquid AI are partnering to enable foundational models on PCs and end-point devices to address the real-world challenges of running AI agents locally. Liquid AI Co-founder and CEO Ramin explains how we are helping make on-device AI practical and accessible.

AMD

20,716 Aufrufe • vor 4 Monaten

🚨$OSS is not an AI company. → It is the hardware that lets AI exist where the cloud cannot. Most investors don’t understand $OSS because they think AI = software. $OSS builds the physical “brains” that run AI in extreme environments where cloud computing fails. Jets. Ships. Tanks. Drones. Space. Hospitals. That’s the game. 1) What $OSS actually is $OSS (One Stop Systems) designs rugged high-performance computers and storage systems for AI at the edge. Meaning: They bring data-center-level computing power into harsh environments. Their products include rugged servers, GPU accelerators, storage arrays, and expansion systems used for AI, sensor processing, and autonomous systems. In simple terms: Cloud AI = brain in a safe building. $OSS AI = brain inside machines operating in chaos. 2) Why this is crucial Most AI today runs in data centers. But the future of AI is not in the cloud. It’s on: • autonomous vehicles • military systems • drones • ships • industrial machines • medical devices These systems cannot wait for the cloud. Latency, connectivity, security, and survival demand local AI. $OSS delivers “data-center performance at the edge” across land, sea, and air. Without companies like OSS, autonomous systems simply don’t work. 3) What OSS actually does: Think of OSS as building AI engines that survive reality. 🌊 SEA example: naval surveillance aircraft and ships. $OSS supplies rugged storage and compute systems for U.S. Navy reconnaissance aircraft to collect and process massive sensor data in real time. Translation: Instead of sending raw data back to base, the aircraft analyzes threats instantly onboard. $OSS = the onboard AI brain. 🪖 LAND example: military vehicles and tactical operations. $OSS delivers high-performance servers and FPGA systems for mobile military intelligence platforms used by the U.S. Department of Defense. Translation: Tanks and vehicles detect threats, process sensor data, and make decisions locally. $OSS = the battlefield computer. ✈️ AIR example: airborne AI. $OSS builds GPU-accelerated servers designed for aircraft, described as a “datacenter in the sky.” Translation: Jets and drones run AI models mid-flight. $OSS = flying supercomputers. 🚀 SPACE example: $OSS hardware is designed for extreme environments and autonomous systems across aerospace and defense. Translation: Future satellites, space drones, and autonomous spacecraft need onboard AI. $OSS = the computing core of autonomous space systems. BONUS: CIVILIAN & COMMERCIAL $OSS systems are used in: • autonomous trucking and farming • industrial automation • healthcare imaging • energy and mining • telecom and 5G Example:A medical imaging company uses $OSS hardware to run real-time AI diagnostics in next-gen breast cancer scanners. $OSS = AI where milliseconds matter. 4) Who their customers are (pattern, not names) $OSS sells to: • defense primes • government programs • industrial OEMs • AI infrastructure companies • medical device manufacturers These customers share one trait: They cannot rely on the cloud. That’s why $OSS exists. 5) The mental model that makes $OSS obvious $NVDA = AI chips $PLTR = AI software $OSS = AI hardware in the real world If AI is electricity, $OSS builds the generators that work in storms. Most investors understand AI software. Few understand AI infrastructure at the edge. That gap is the opportunity. 6) The real thesis The world is moving toward: • autonomous warfare • autonomous vehicles • real-time AI systems • distributed intelligence All of that requires rugged edge computing. $OSS is positioned exactly there. Infrastructure. The hardest layer to build. And often the most valuable.
0:51

🚨$OSS is not an AI company. → It is the hardware that lets AI exist where the cloud cannot. Most investors don’t understand $OSS because they think AI = software. $OSS builds the physical “brains” that run AI in extreme environments where cloud computing fails. Jets. Ships. Tanks. Drones. Space. Hospitals. That’s the game. 1) What $OSS actually is $OSS (One Stop Systems) designs rugged high-performance computers and storage systems for AI at the edge. Meaning: They bring data-center-level computing power into harsh environments. Their products include rugged servers, GPU accelerators, storage arrays, and expansion systems used for AI, sensor processing, and autonomous systems. In simple terms: Cloud AI = brain in a safe building. $OSS AI = brain inside machines operating in chaos. 2) Why this is crucial Most AI today runs in data centers. But the future of AI is not in the cloud. It’s on: • autonomous vehicles • military systems • drones • ships • industrial machines • medical devices These systems cannot wait for the cloud. Latency, connectivity, security, and survival demand local AI. $OSS delivers “data-center performance at the edge” across land, sea, and air. Without companies like OSS, autonomous systems simply don’t work. 3) What OSS actually does: Think of OSS as building AI engines that survive reality. 🌊 SEA example: naval surveillance aircraft and ships. $OSS supplies rugged storage and compute systems for U.S. Navy reconnaissance aircraft to collect and process massive sensor data in real time. Translation: Instead of sending raw data back to base, the aircraft analyzes threats instantly onboard. $OSS = the onboard AI brain. 🪖 LAND example: military vehicles and tactical operations. $OSS delivers high-performance servers and FPGA systems for mobile military intelligence platforms used by the U.S. Department of Defense. Translation: Tanks and vehicles detect threats, process sensor data, and make decisions locally. $OSS = the battlefield computer. ✈️ AIR example: airborne AI. $OSS builds GPU-accelerated servers designed for aircraft, described as a “datacenter in the sky.” Translation: Jets and drones run AI models mid-flight. $OSS = flying supercomputers. 🚀 SPACE example: $OSS hardware is designed for extreme environments and autonomous systems across aerospace and defense. Translation: Future satellites, space drones, and autonomous spacecraft need onboard AI. $OSS = the computing core of autonomous space systems. BONUS: CIVILIAN & COMMERCIAL $OSS systems are used in: • autonomous trucking and farming • industrial automation • healthcare imaging • energy and mining • telecom and 5G Example:A medical imaging company uses $OSS hardware to run real-time AI diagnostics in next-gen breast cancer scanners. $OSS = AI where milliseconds matter. 4) Who their customers are (pattern, not names) $OSS sells to: • defense primes • government programs • industrial OEMs • AI infrastructure companies • medical device manufacturers These customers share one trait: They cannot rely on the cloud. That’s why $OSS exists. 5) The mental model that makes $OSS obvious $NVDA = AI chips $PLTR = AI software $OSS = AI hardware in the real world If AI is electricity, $OSS builds the generators that work in storms. Most investors understand AI software. Few understand AI infrastructure at the edge. That gap is the opportunity. 6) The real thesis The world is moving toward: • autonomous warfare • autonomous vehicles • real-time AI systems • distributed intelligence All of that requires rugged edge computing. $OSS is positioned exactly there. Infrastructure. The hardest layer to build. And often the most valuable.

Black Panther Capital

30,138 Aufrufe • vor 5 Monaten

Open AI released Operator, an agent that can use the browser to perform and automate tasks for you! I have built an Open Source version of Operator using Browser Use, running locally on your computer. 100% Open Source
0:59

Open AI released Operator, an agent that can use the browser to perform and automate tasks for you! I have built an Open Source version of Operator using Browser Use, running locally on your computer. 100% Open Source

Sumanth

62,485 Aufrufe • vor 1 Jahr

Introducing the OpenAI Podcast—a series of conversations with the people shaping AI. Sam Altman joins @andrewmayne on the first episode to talk about AGI, (wen) GPT-5, privacy, and what comes next.
40:23

Introducing the OpenAI Podcast—a series of conversations with the people shaping AI. Sam Altman joins @andrewmayne on the first episode to talk about AGI, (wen) GPT-5, privacy, and what comes next.

OpenAI

2,110,889 Aufrufe • vor 1 Jahr

SecureGPT Mobile Integration We are thrilled to announce that SecureGPT will be fully integrated with EdgeAI on iOS, bringing our powerful privacy protections directly to your mobile devices! This isn't just another app update - it's a fundamental shift in how you can interact with AI on mobile: • Anonymous Authentication: Your device connects to our services without revealing your identity - even to us • TOR-Protected Queries: Every AI interaction is routed through secure TOR circuits, ensuring complete network privacy • On-Device Sanitization: Your sensitive information is filtered locally before leaving your phone For too long, mobile AI has meant sacrificing privacy. Soon, that changes. Whether you are researching sensitive topics, handling confidential work, or simply value your privacy, you can access the full power of AI without compromising your data.
0:57

SecureGPT Mobile Integration We are thrilled to announce that SecureGPT will be fully integrated with EdgeAI on iOS, bringing our powerful privacy protections directly to your mobile devices! This isn't just another app update - it's a fundamental shift in how you can interact with AI on mobile: • Anonymous Authentication: Your device connects to our services without revealing your identity - even to us • TOR-Protected Queries: Every AI interaction is routed through secure TOR circuits, ensuring complete network privacy • On-Device Sanitization: Your sensitive information is filtered locally before leaving your phone For too long, mobile AI has meant sacrificing privacy. Soon, that changes. Whether you are researching sensitive topics, handling confidential work, or simply value your privacy, you can access the full power of AI without compromising your data.

ZKCrypt AI

14,343 Aufrufe • vor 1 Jahr

gpt-oss with built-in websearch in ollama running fully locally on my mac with Exa for search shoutout to @DKundel OpenAI Developers for making it so easy :)
1:01

gpt-oss with built-in websearch in ollama running fully locally on my mac with Exa for search shoutout to @DKundel OpenAI Developers for making it so easy :)

parth

19,807 Aufrufe • vor 10 Monaten

Sam Altman says GPT-3 was the first real glimpse of passing a spiritual Turing test GPT-5 shows the first small signs of AI doing new science — useful ideas, real help on papers GPT-6 will be a leap like GPT-3 to 4, but this time for science, where it can really do it
0:35

Sam Altman says GPT-3 was the first real glimpse of passing a spiritual Turing test GPT-5 shows the first small signs of AI doing new science — useful ideas, real help on papers GPT-6 will be a leap like GPT-3 to 4, but this time for science, where it can really do it

Haider.

163,642 Aufrufe • vor 7 Monaten

On "Introduction to On-Device AI," made in collaboration with Qualcomm, you’ll become proficient in deploying AI where it's needed most—right on your mobile device. Sign up for our waitlist and be the first to enroll!
0:23

On "Introduction to On-Device AI," made in collaboration with Qualcomm, you’ll become proficient in deploying AI where it's needed most—right on your mobile device. Sign up for our waitlist and be the first to enroll!

DeepLearning.AI

27,881 Aufrufe • vor 2 Jahren